Journal of KIISE (정보과학회 논문지)

Korean Institute of Information Scientists and Engineers (한국정보과학회)
권호 표지
DOI QR코드

DOI QR Code

Value Weighted Regularized Logistic Regression Model

속성값 기반의 정규화된 로지스틱 회귀분석 모델

  • Received : 2016.07.25
  • Accepted : 2016.09.13
  • Published : 2016.11.15
⟨ Previous Next ⟩

Abstract

Logistic regression is widely used for predicting and estimating the relationship among variables. We propose a new logistic regression model, the value weighted logistic regression, which comprises of a fine-grained weighting method, and assigns adapted weights to each feature value. This gradient approach obtains the optimal weights of feature values. Experiments were conducted on several data sets from the UCI machine learning repository, and the results revealed that the proposed method achieves meaningful improvement in the prediction accuracy.

로지스틱 회귀분석은 통계학 등의 분야에서 예측을 위한 기술 혹은 변수 간의 상관관계를 설명하기 위하여 오랫동안 사용되어 왔다. 이러한 로지스틱 회귀분석 방법에서 현재 각 속성들은 목적 값에 대하여 동일한 중요도를 가지고 있다. 본 연구에서는 이러한 가중치 계산을 좀더 세분화하여 각 속성의 값이 서로 다른 중요도를 가지는 새로운 학습 방법을 제시한다. 알고리즘의 성능을 최대화하는 각 속성값 가중치의 값을 계산하기 위하여 점진적 하강법을 이용하여 개발하였다. 본 연구에서 제안된 방법은 다양한 데이터를 이용하여 실험하였고 속성값 기반 로지스틱 회귀분석 방법은 기존의 로지스틱 회귀분석보다 우수한 학습 능력을 보임을 알 수 있었다.

Keywords

Acknowledgement

Supported by : 한국연구재단

References

  1. Menard, Scott, Applied logistic regression analysis, Vol. 106, Sage, 2002.
  2. Atkeson, Christopher G., Andrew W. Moore, and Stefan Schaal, "Locally weighted learning for control," Lazy learning, Springer Netherlands, 75-113, 1997.
  3. Cleveland, William S., and Susan J. Devlin, "Locally weighted regression: an approach to regression analysis by local fitting," Journal of the American Statistical Association 83.403 (1988): 596-610. https://doi.org/10.1080/01621459.1988.10478639
  4. Zhang, Lijun, et al., "Efficient Online Learning for Large-Scale Sparse Kernel Logistic Regression," AAAI, 2012.
  5. Zhu, Ji, and Trevor Hastie, "Kernel logistic regression and the import vector machine," Journal of Computational and Graphical Statistics (2005).
  6. Hosmer D W, Lemesbow S. Goodness of fit tests for the multiple logistic regression model, Communications in Statistics-Theory and Methods, 9(10), pp. 1043-1069, 1980. https://doi.org/10.1080/03610928008827941
  7. Goeman, Jelle, Rosa Meijer, and Nimisha Chaturvedi, "L1 and L2 penalized regression models," 2014.
  8. Hosmer Jr, David W., and Stanley Lemeshow, Applied logistic regression, John Wiley & Sons, 2004.
  9. https://archive.ics.uci.edu/ml/datasets.html
  10. Kurgan, Lukasz, and Krzysztof J. Cios, "CAIM discretization algorithm," Knowledge and Data Engineering, IEEE Transactions on Knowledge and Data Engineering, pp. 145-153, 2004.